korsygfhrtzangaiide

--- linux-2.6.22.orig/fs/autofs4/root.c +++ linux-2.6.22/fs/autofs4/root.c @@ -25,25 +25,25 @@ static int autofs4_dir_rmdir(struct inod static int autofs4_dir_mkdir(struct inode *,struct dentry *,int); static int autofs4_root_ioctl(struct inode *, struct file *,unsigned int,unsigned long); static int autofs4_dir_open(struct inode *inode, struct file *file); -static int autofs4_dir_close(struct inode *inode, struct file *file); -static int autofs4_dir_readdir(struct file * filp, void * dirent, filldir_t filldir); -static int autofs4_root_readdir(struct file * filp, void * dirent, filldir_t filldir); static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *); static void *autofs4_follow_link(struct dentry *, struct nameidata *); +#define TRIGGER_FLAGS (LOOKUP_CONTINUE | LOOKUP_DIRECTORY) +#define TRIGGER_INTENTS (LOOKUP_OPEN | LOOKUP_CREATE) + const struct file_operations autofs4_root_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .read = generic_read_dir, - .readdir = autofs4_root_readdir, + .readdir = dcache_readdir, .ioctl = autofs4_root_ioctl, }; const struct file_operations autofs4_dir_operations = { .open = autofs4_dir_open, - .release = autofs4_dir_close, + .release = dcache_dir_close, .read = generic_read_dir, - .readdir = autofs4_dir_readdir, + .readdir = dcache_readdir, }; const struct inode_operations autofs4_indirect_root_inode_operations = { @@ -70,42 +70,10 @@ const struct inode_operations autofs4_di .rmdir = autofs4_dir_rmdir, }; -static int autofs4_root_readdir(struct file *file, void *dirent, - filldir_t filldir) -{ - struct autofs_sb_info *sbi = autofs4_sbi(file->f_path.dentry->d_sb); - int oz_mode = autofs4_oz_mode(sbi); - - DPRINTK("called, filp->f_pos = %lld", file->f_pos); - - /* - * Don't set reghost flag if: - * 1) f_pos is larger than zero -- we've already been here. - * 2) we haven't even enabled reghosting in the 1st place. - * 3) this is the daemon doing a readdir - */ - if (oz_mode && file->f_pos == 0 && sbi->reghost_enabled) - sbi->needs_reghost = 1; - - DPRINTK("needs_reghost = %d", sbi->needs_reghost); - - return dcache_readdir(file, dirent, filldir); -} - static int autofs4_dir_open(struct inode *inode, struct file *file) { struct dentry *dentry = file->f_path.dentry; - struct vfsmount *mnt = file->f_path.mnt; struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct dentry *cursor; - int status; - - status = dcache_dir_open(inode, file); - if (status) - goto out; - - cursor = file->private_data; - cursor->d_fsdata = NULL; DPRINTK("file=%p dentry=%p %.*s", file, dentry, dentry->d_name.len, dentry->d_name.name); @@ -113,157 +81,31 @@ static int autofs4_dir_open(struct inode if (autofs4_oz_mode(sbi)) goto out; - if (autofs4_ispending(dentry)) { - DPRINTK("dentry busy"); - dcache_dir_close(inode, file); - status = -EBUSY; - goto out; - } - - status = -ENOENT; - if (!d_mountpoint(dentry) && dentry->d_op && dentry->d_op->d_revalidate) { - struct nameidata nd; - int empty, ret; - - /* In case there are stale directory dentrys from a failed mount */ - spin_lock(&dcache_lock); - empty = list_empty(&dentry->d_subdirs); + /* + * An empty directory in an autofs file system is always a + * mount point. The daemon must have failed to mount this + * during lookup so it doesn't exist. This can happen, for + * example, if user space returns an incorrect status for a + * mount request. Otherwise we're doing a readdir on the + * autofs file system so just let the libfs routines handle + * it. + */ + spin_lock(&dcache_lock); + if (!d_mountpoint(dentry) && __simple_empty(dentry)) { spin_unlock(&dcache_lock); - - if (!empty) - d_invalidate(dentry); - - nd.flags = LOOKUP_DIRECTORY; - ret = (dentry->d_op->d_revalidate)(dentry, &nd); - - if (ret <= 0) { - if (ret < 0) - status = ret; - dcache_dir_close(inode, file); - goto out; - } - } - - if (d_mountpoint(dentry)) { - struct file *fp = NULL; - struct vfsmount *fp_mnt = mntget(mnt); - struct dentry *fp_dentry = dget(dentry); - - if (!autofs4_follow_mount(&fp_mnt, &fp_dentry)) { - dput(fp_dentry); - mntput(fp_mnt); - dcache_dir_close(inode, file); - goto out; - } - - fp = dentry_open(fp_dentry, fp_mnt, file->f_flags); - status = PTR_ERR(fp); - if (IS_ERR(fp)) { - dcache_dir_close(inode, file); - goto out; - } - cursor->d_fsdata = fp; - } - return 0; -out: - return status; -} - -static int autofs4_dir_close(struct inode *inode, struct file *file) -{ - struct dentry *dentry = file->f_path.dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct dentry *cursor = file->private_data; - int status = 0; - - DPRINTK("file=%p dentry=%p %.*s", - file, dentry, dentry->d_name.len, dentry->d_name.name); - - if (autofs4_oz_mode(sbi)) - goto out; - - if (autofs4_ispending(dentry)) { - DPRINTK("dentry busy"); - status = -EBUSY; - goto out; - } - - if (d_mountpoint(dentry)) { - struct file *fp = cursor->d_fsdata; - if (!fp) { - status = -ENOENT; - goto out; - } - filp_close(fp, current->files); - } -out: - dcache_dir_close(inode, file); - return status; -} - -static int autofs4_dir_readdir(struct file *file, void *dirent, filldir_t filldir) -{ - struct dentry *dentry = file->f_path.dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct dentry *cursor = file->private_data; - int status; - - DPRINTK("file=%p dentry=%p %.*s", - file, dentry, dentry->d_name.len, dentry->d_name.name); - - if (autofs4_oz_mode(sbi)) - goto out; - - if (autofs4_ispending(dentry)) { - DPRINTK("dentry busy"); - return -EBUSY; + return -ENOENT; } + spin_unlock(&dcache_lock); - if (d_mountpoint(dentry)) { - struct file *fp = cursor->d_fsdata; - - if (!fp) - return -ENOENT; - - if (!fp->f_op || !fp->f_op->readdir) - goto out; - - status = vfs_readdir(fp, filldir, dirent); - file->f_pos = fp->f_pos; - if (status) - autofs4_copy_atime(file, fp); - return status; - } out: - return dcache_readdir(file, dirent, filldir); + return dcache_dir_open(inode, file); } static int try_to_fill_dentry(struct dentry *dentry, int flags) { struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); - int status = 0; - - /* Block on any pending expiry here; invalidate the dentry - when expiration is done to trigger mount request with a new - dentry */ - if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) { - DPRINTK("waiting for expire %p name=%.*s", - dentry, dentry->d_name.len, dentry->d_name.name); - - status = autofs4_wait(sbi, dentry, NFY_NONE); - - DPRINTK("expire done status=%d", status); - - /* - * If the directory still exists the mount request must - * continue otherwise it can't be followed at the right - * time during the walk. - */ - status = d_invalidate(dentry); - if (status != -EBUSY) - return -EAGAIN; - } + int status; DPRINTK("dentry=%p %.*s ino=%p", dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode); @@ -291,7 +133,8 @@ static int try_to_fill_dentry(struct den return status; } /* Trigger mount for path component or follow link */ - } else if (flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY) || + } else if (dentry->d_flags & DCACHE_AUTOFS_PENDING || + flags & (TRIGGER_FLAGS | TRIGGER_INTENTS) || current->link_count) { DPRINTK("waiting for mount name=%.*s", dentry->d_name.len, dentry->d_name.name); @@ -318,7 +161,8 @@ static int try_to_fill_dentry(struct den spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; spin_unlock(&dentry->d_lock); - return status; + + return 0; } /* For autofs direct mounts the follow link triggers the mount */ @@ -333,50 +177,62 @@ static void *autofs4_follow_link(struct DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d", dentry, dentry->d_name.len, dentry->d_name.name, oz_mode, nd->flags); - - /* If it's our master or we shouldn't trigger a mount we're done */ - lookup_type = nd->flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY); - if (oz_mode || !lookup_type) + /* + * For an expire of a covered direct or offset mount we need + * to beeak out of follow_down() at the autofs mount trigger + * (d_mounted--), so we can see the expiring flag, and manage + * the blocking and following here until the expire is completed. + */ + if (oz_mode) { + spin_lock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_EXPIRING) { + spin_unlock(&sbi->fs_lock); + /* Follow down to our covering mount. */ + if (!follow_down(&nd->mnt, &nd->dentry)) + goto done; + goto follow; + } + spin_unlock(&sbi->fs_lock); goto done; + } - /* If an expire request is pending wait for it. */ - if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) { - DPRINTK("waiting for active request %p name=%.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + /* If an expire request is pending everyone must wait. */ + autofs4_expire_wait(dentry); - status = autofs4_wait(sbi, dentry, NFY_NONE); - - DPRINTK("request done status=%d", status); - } + /* We trigger a mount for almost all flags */ + lookup_type = nd->flags & (TRIGGER_FLAGS | TRIGGER_INTENTS); + if (!(lookup_type || dentry->d_flags & DCACHE_AUTOFS_PENDING)) + goto follow; /* - * If the dentry contains directories then it is an - * autofs multi-mount with no root mount offset. So - * don't try to mount it again. + * If the dentry contains directories then it is an autofs + * multi-mount with no root mount offset. So don't try to + * mount it again. */ spin_lock(&dcache_lock); - if (!d_mountpoint(dentry) && __simple_empty(dentry)) { + if (dentry->d_flags & DCACHE_AUTOFS_PENDING || + (!d_mountpoint(dentry) && __simple_empty(dentry))) { spin_unlock(&dcache_lock); status = try_to_fill_dentry(dentry, 0); if (status) goto out_error; - /* - * The mount succeeded but if there is no root mount - * it must be an autofs multi-mount with no root offset - * so we don't need to follow the mount. - */ - if (d_mountpoint(dentry)) { - if (!autofs4_follow_mount(&nd->mnt, &nd->dentry)) { - status = -ENOENT; - goto out_error; - } - } - - goto done; + goto follow; } spin_unlock(&dcache_lock); +follow: + /* + * If there is no root mount it must be an autofs + * multi-mount with no root offset so we don't need + * to follow it. + */ + if (d_mountpoint(dentry)) { + if (!autofs4_follow_mount(&nd->mnt, &nd->dentry)) { + status = -ENOENT; + goto out_error; + } + } done: return NULL; @@ -401,12 +257,23 @@ static int autofs4_revalidate(struct den int status = 1; /* Pending dentry */ + spin_lock(&sbi->fs_lock); if (autofs4_ispending(dentry)) { /* The daemon never causes a mount to trigger */ + spin_unlock(&sbi->fs_lock); + if (oz_mode) return 1; /* + * If the directory has gone away due to an expire + * we have been called as ->d_revalidate() and so + * we need to return false and proceed to ->lookup(). + */ + if (autofs4_expire_wait(dentry) == -EAGAIN) + return 0; + + /* * A zero status is success otherwise we have a * negative error code. */ @@ -414,17 +281,9 @@ static int autofs4_revalidate(struct den if (status == 0) return 1; - /* - * A status of EAGAIN here means that the dentry has gone - * away while waiting for an expire to complete. If we are - * racing with expire lookup will wait for it so this must - * be a revalidate and we need to send it to lookup. - */ - if (status == -EAGAIN) - return 0; - return status; } + spin_unlock(&sbi->fs_lock); /* Negative dentry.. invalidate if "old" */ if (dentry->d_inode == NULL) @@ -438,6 +297,7 @@ static int autofs4_revalidate(struct den DPRINTK("dentry=%p %.*s, emptydir", dentry, dentry->d_name.len, dentry->d_name.name); spin_unlock(&dcache_lock); + /* The daemon never causes a mount to trigger */ if (oz_mode) return 1; @@ -470,10 +330,12 @@ void autofs4_dentry_release(struct dentr struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb); if (sbi) { - spin_lock(&sbi->rehash_lock); - if (!list_empty(&inf->rehash)) - list_del(&inf->rehash); - spin_unlock(&sbi->rehash_lock); + spin_lock(&sbi->lookup_lock); + if (!list_empty(&inf->active)) + list_del(&inf->active); + if (!list_empty(&inf->expiring)) + list_del(&inf->expiring); + spin_unlock(&sbi->lookup_lock); } inf->dentry = NULL; @@ -495,7 +357,59 @@ static struct dentry_operations autofs4_ .d_release = autofs4_dentry_release, }; -static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name) +static struct dentry *autofs4_lookup_active(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name) +{ + unsigned int len = name->len; + unsigned int hash = name->hash; + const unsigned char *str = name->name; + struct list_head *p, *head; + + spin_lock(&dcache_lock); + spin_lock(&sbi->lookup_lock); + head = &sbi->active_list; + list_for_each(p, head) { + struct autofs_info *ino; + struct dentry *dentry; + struct qstr *qstr; + + ino = list_entry(p, struct autofs_info, active); + dentry = ino->dentry; + + spin_lock(&dentry->d_lock); + + /* Already gone? */ + if (atomic_read(&dentry->d_count) == 0) + goto next; + + qstr = &dentry->d_name; + + if (dentry->d_name.hash != hash) + goto next; + if (dentry->d_parent != parent) + goto next; + + if (qstr->len != len) + goto next; + if (memcmp(qstr->name, str, len)) + goto next; + + if (d_unhashed(dentry)) { + dget(dentry); + spin_unlock(&dentry->d_lock); + spin_unlock(&sbi->lookup_lock); + spin_unlock(&dcache_lock); + return dentry; + } +next: + spin_unlock(&dentry->d_lock); + } + spin_unlock(&sbi->lookup_lock); + spin_unlock(&dcache_lock); + + return NULL; +} + +static struct dentry *autofs4_lookup_expiring(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name) { unsigned int len = name->len; unsigned int hash = name->hash; @@ -503,14 +417,14 @@ static struct dentry *autofs4_lookup_unh struct list_head *p, *head; spin_lock(&dcache_lock); - spin_lock(&sbi->rehash_lock); - head = &sbi->rehash_list; + spin_lock(&sbi->lookup_lock); + head = &sbi->expiring_list; list_for_each(p, head) { struct autofs_info *ino; struct dentry *dentry; struct qstr *qstr; - ino = list_entry(p, struct autofs_info, rehash); + ino = list_entry(p, struct autofs_info, expiring); dentry = ino->dentry; spin_lock(&dentry->d_lock); @@ -532,33 +446,16 @@ static struct dentry *autofs4_lookup_unh goto next; if (d_unhashed(dentry)) { - struct autofs_info *ino = autofs4_dentry_ino(dentry); - struct inode *inode = dentry->d_inode; - - list_del_init(&ino->rehash); dget(dentry); - /* - * Make the rehashed dentry negative so the VFS - * behaves as it should. - */ - if (inode) { - dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); - spin_unlock(&dentry->d_lock); - spin_unlock(&sbi->rehash_lock); - spin_unlock(&dcache_lock); - iput(inode); - return dentry; - } spin_unlock(&dentry->d_lock); - spin_unlock(&sbi->rehash_lock); + spin_unlock(&sbi->lookup_lock); spin_unlock(&dcache_lock); return dentry; } next: spin_unlock(&dentry->d_lock); } - spin_unlock(&sbi->rehash_lock); + spin_unlock(&sbi->lookup_lock); spin_unlock(&dcache_lock); return NULL; @@ -568,7 +465,8 @@ next: static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { struct autofs_sb_info *sbi; - struct dentry *unhashed; + struct autofs_info *ino; + struct dentry *expiring, *unhashed; int oz_mode; DPRINTK("name = %.*s", @@ -584,50 +482,67 @@ static struct dentry *autofs4_lookup(str DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d", current->pid, process_group(current), sbi->catatonic, oz_mode); - unhashed = autofs4_lookup_unhashed(sbi, dentry->d_parent, &dentry->d_name); - if (!unhashed) { + unhashed = autofs4_lookup_active(sbi, dentry->d_parent, &dentry->d_name); + if (unhashed) + dentry = unhashed; + else { /* - * Mark the dentry incomplete, but add it. This is needed so - * that the VFS layer knows about the dentry, and we can count - * on catching any lookups through the revalidate. - * - * Let all the hard work be done by the revalidate function that - * needs to be able to do this anyway.. - * - * We need to do this before we release the directory semaphore. + * Mark the dentry incomplete but don't hash it. We do this + * to serialize our inode creation operations (symlink and + * mkdir) which prevents deadlock during the callback to + * the daemon. Subsequent user space lookups for the same + * dentry are placed on the wait queue while the daemon + * itself is allowed passage unresticted so the create + * operation itself can then hash the dentry. Finally, + * we check for the hashed dentry and return the newly + * hashed dentry. */ dentry->d_op = &autofs4_root_dentry_operations; - dentry->d_fsdata = NULL; - d_add(dentry, NULL); - } else { - struct autofs_info *ino = autofs4_dentry_ino(unhashed); - DPRINTK("rehash %p with %p", dentry, unhashed); /* - * If we are racing with expire the request might not - * be quite complete but the directory has been removed - * so it must have been successful, so just wait for it. + * And we need to ensure that the same dentry is used for + * all following lookup calls until it is hashed so that + * the dentry flags are persistent throughout the request. */ - if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) { - DPRINTK("wait for incomplete expire %p name=%.*s", - unhashed, unhashed->d_name.len, - unhashed->d_name.name); - autofs4_wait(sbi, unhashed, NFY_NONE); - DPRINTK("request completed"); - } - d_rehash(unhashed); - dentry = unhashed; + ino = autofs4_init_ino(NULL, sbi, 0555); + if (!ino) + return ERR_PTR(-ENOMEM); + + dentry->d_fsdata = ino; + ino->dentry = dentry; + + spin_lock(&sbi->lookup_lock); + list_add(&ino->active, &sbi->active_list); + spin_unlock(&sbi->lookup_lock); + + d_instantiate(dentry, NULL); } if (!oz_mode) { + mutex_unlock(&dir->i_mutex); + expiring = autofs4_lookup_expiring(sbi, + dentry->d_parent, + &dentry->d_name); + if (expiring) { + /* + * If we are racing with expire the request might not + * be quite complete but the directory has been removed + * so it must have been successful, so just wait for it. + */ + ino = autofs4_dentry_ino(expiring); + autofs4_expire_wait(expiring); + spin_lock(&sbi->lookup_lock); + if (!list_empty(&ino->expiring)) + list_del_init(&ino->expiring); + spin_unlock(&sbi->lookup_lock); + dput(expiring); + } + spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_AUTOFS_PENDING; spin_unlock(&dentry->d_lock); - } - - if (dentry->d_op && dentry->d_op->d_revalidate) { - mutex_unlock(&dir->i_mutex); - (dentry->d_op->d_revalidate)(dentry, nd); + if (dentry->d_op && dentry->d_op->d_revalidate) + (dentry->d_op->d_revalidate)(dentry, nd); mutex_lock(&dir->i_mutex); } @@ -647,9 +562,11 @@ static struct dentry *autofs4_lookup(str return ERR_PTR(-ERESTARTNOINTR); } } - spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); + if (!oz_mode) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; + spin_unlock(&dentry->d_lock); + } } /* @@ -658,7 +575,7 @@ static struct dentry *autofs4_lookup(str * for all system calls, but it should be OK for the operations * we permit from an autofs. */ - if (dentry->d_inode && d_unhashed(dentry)) { + if (!oz_mode && d_unhashed(dentry)) { /* * A user space application can (and has done in the past) * remove and re-create this directory during the callback. @@ -680,7 +597,7 @@ static struct dentry *autofs4_lookup(str } if (unhashed) - return dentry; + return unhashed; return NULL; } @@ -702,21 +619,32 @@ static int autofs4_dir_symlink(struct in return -EACCES; ino = autofs4_init_ino(ino, sbi, S_IFLNK | 0555); - if (ino == NULL) - return -ENOSPC; + if (!ino) + return -ENOMEM; - ino->size = strlen(symname); - ino->u.symlink = cp = kmalloc(ino->size + 1, GFP_KERNEL); + spin_lock(&sbi->lookup_lock); + if (!list_empty(&ino->active)) + list_del_init(&ino->active); + spin_unlock(&sbi->lookup_lock); - if (cp == NULL) { - kfree(ino); - return -ENOSPC; + ino->size = strlen(symname); + cp = kmalloc(ino->size + 1, GFP_KERNEL); + if (!cp) { + if (!dentry->d_fsdata) + kfree(ino); + return -ENOMEM; } strcpy(cp, symname); inode = autofs4_get_inode(dir->i_sb, ino); - d_instantiate(dentry, inode); + if (!inode) { + kfree(cp); + if (!dentry->d_fsdata) + kfree(ino); + return -ENOMEM; + } + d_add(dentry, inode); if (dir == dir->i_sb->s_root->d_inode) dentry->d_op = &autofs4_root_dentry_operations; @@ -731,6 +659,7 @@ static int autofs4_dir_symlink(struct in atomic_inc(&p_ino->count); ino->inode = inode; + ino->u.symlink = cp; dir->i_mtime = CURRENT_TIME; return 0; @@ -743,9 +672,8 @@ static int autofs4_dir_symlink(struct in * that the file no longer exists. However, doing that means that the * VFS layer can turn the dentry into a negative dentry. We don't want * this, because the unlink is probably the result of an expire. - * We simply d_drop it and add it to a rehash candidates list in the - * super block, which allows the dentry lookup to reuse it retaining - * the flags, such as expire in progress, in case we're racing with expire. + * We simply d_drop it and add it to a expiring list in the super block, + * which allows the dentry lookup to check for an incomplete expire. * * If a process is blocked on the dentry waiting for the expire to finish, * it will invalidate the dentry and try to mount with a new one. @@ -775,9 +703,10 @@ static int autofs4_dir_unlink(struct ino dir->i_mtime = CURRENT_TIME; spin_lock(&dcache_lock); - spin_lock(&sbi->rehash_lock); - list_add(&ino->rehash, &sbi->rehash_list); - spin_unlock(&sbi->rehash_lock); + spin_lock(&sbi->lookup_lock); + if (list_empty(&ino->expiring)) + list_add(&ino->expiring, &sbi->expiring_list); + spin_unlock(&sbi->lookup_lock); spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); @@ -803,9 +732,10 @@ static int autofs4_dir_rmdir(struct inod spin_unlock(&dcache_lock); return -ENOTEMPTY; } - spin_lock(&sbi->rehash_lock); - list_add(&ino->rehash, &sbi->rehash_list); - spin_unlock(&sbi->rehash_lock); + spin_lock(&sbi->lookup_lock); + if (list_empty(&ino->expiring)) + list_add(&ino->expiring, &sbi->expiring_list); + spin_unlock(&sbi->lookup_lock); spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); @@ -840,11 +770,21 @@ static int autofs4_dir_mkdir(struct inod dentry, dentry->d_name.len, dentry->d_name.name); ino = autofs4_init_ino(ino, sbi, S_IFDIR | 0555); - if (ino == NULL) - return -ENOSPC; + if (!ino) + return -ENOMEM; + + spin_lock(&sbi->lookup_lock); + if (!list_empty(&ino->active)) + list_del_init(&ino->active); + spin_unlock(&sbi->lookup_lock); inode = autofs4_get_inode(dir->i_sb, ino); - d_instantiate(dentry, inode); + if (!inode) { + if (!dentry->d_fsdata) + kfree(ino); + return -ENOMEM; + } + d_add(dentry, inode); if (dir == dir->i_sb->s_root->d_inode) dentry->d_op = &autofs4_root_dentry_operations; @@ -896,44 +836,6 @@ static inline int autofs4_get_protosubve } /* - * Tells the daemon whether we need to reghost or not. Also, clears - * the reghost_needed flag. - */ -static inline int autofs4_ask_reghost(struct autofs_sb_info *sbi, int __user *p) -{ - int status; - - DPRINTK("returning %d", sbi->needs_reghost); - - status = put_user(sbi->needs_reghost, p); - if (status) - return status; - - sbi->needs_reghost = 0; - return 0; -} - -/* - * Enable / Disable reghosting ioctl() operation - */ -static inline int autofs4_toggle_reghost(struct autofs_sb_info *sbi, int __user *p) -{ - int status; - int val; - - status = get_user(val, p); - - DPRINTK("reghost = %d", val); - - if (status) - return status; - - /* turn on/off reghosting, with the val */ - sbi->reghost_enabled = val; - return 0; -} - -/* * Tells the daemon whether it can umount the autofs mount. */ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p) @@ -997,11 +899,6 @@ static int autofs4_root_ioctl(struct ino case AUTOFS_IOC_SETTIMEOUT: return autofs4_get_set_timeout(sbi, p); - case AUTOFS_IOC_TOGGLEREGHOST: - return autofs4_toggle_reghost(sbi, p); - case AUTOFS_IOC_ASKREGHOST: - return autofs4_ask_reghost(sbi, p); - case AUTOFS_IOC_ASKUMOUNT: return autofs4_ask_umount(filp->f_path.mnt, p); --- linux-2.6.22.orig/fs/autofs4/waitq.c +++ linux-2.6.22/fs/autofs4/waitq.c @@ -28,6 +28,12 @@ void autofs4_catatonic_mode(struct autof { struct autofs_wait_queue *wq, *nwq; + mutex_lock(&sbi->wq_mutex); + if (sbi->catatonic) { + mutex_unlock(&sbi->wq_mutex); + return; + } + DPRINTK("entering catatonic mode"); sbi->catatonic = 1; @@ -36,13 +42,18 @@ void autofs4_catatonic_mode(struct autof while (wq) { nwq = wq->next; wq->status = -ENOENT; /* Magic is gone - report failure */ - kfree(wq->name); - wq->name = NULL; + if (wq->name.name) { + kfree(wq->name.name); + wq->name.name = NULL; + } + wq->wait_ctr--; wake_up_interruptible(&wq->queue); wq = nwq; } fput(sbi->pipe); /* Close the pipe */ sbi->pipe = NULL; + sbi->pipefd = -1; + mutex_unlock(&sbi->wq_mutex); } static int autofs4_write(struct file *file, const void *addr, int bytes) @@ -89,10 +100,11 @@ static void autofs4_notify_daemon(struct union autofs_packet_union v4_pkt; union autofs_v5_packet_union v5_pkt; } pkt; + struct file *pipe = NULL; size_t pktsz; DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d", - wq->wait_queue_token, wq->len, wq->name, type); + wq->wait_queue_token, wq->name.len, wq->name.name, type); memset(&pkt,0,sizeof pkt); /* For security reasons */ @@ -107,9 +119,9 @@ static void autofs4_notify_daemon(struct pktsz = sizeof(*mp); mp->wait_queue_token = wq->wait_queue_token; - mp->len = wq->len; - memcpy(mp->name, wq->name, wq->len); - mp->name[wq->len] = '\0'; + mp->len = wq->name.len; + memcpy(mp->name, wq->name.name, wq->name.len); + mp->name[wq->name.len] = '\0'; break; } case autofs_ptype_expire_multi: @@ -119,9 +131,9 @@ static void autofs4_notify_daemon(struct pktsz = sizeof(*ep); ep->wait_queue_token = wq->wait_queue_token; - ep->len = wq->len; - memcpy(ep->name, wq->name, wq->len); - ep->name[wq->len] = '\0'; + ep->len = wq->name.len; + memcpy(ep->name, wq->name.name, wq->name.len); + ep->name[wq->name.len] = '\0'; break; } /* @@ -138,9 +150,9 @@ static void autofs4_notify_daemon(struct pktsz = sizeof(*packet); packet->wait_queue_token = wq->wait_queue_token; - packet->len = wq->len; - memcpy(packet->name, wq->name, wq->len); - packet->name[wq->len] = '\0'; + packet->len = wq->name.len; + memcpy(packet->name, wq->name.name, wq->name.len); + packet->name[wq->name.len] = '\0'; packet->dev = wq->dev; packet->ino = wq->ino; packet->uid = wq->uid; @@ -154,8 +166,19 @@ static void autofs4_notify_daemon(struct return; } - if (autofs4_write(sbi->pipe, &pkt, pktsz)) - autofs4_catatonic_mode(sbi); + /* Check if we have become catatonic */ + mutex_lock(&sbi->wq_mutex); + if (!sbi->catatonic) { + pipe = sbi->pipe; + get_file(pipe); + } + mutex_unlock(&sbi->wq_mutex); + + if (pipe) { + if (autofs4_write(pipe, &pkt, pktsz)) + autofs4_catatonic_mode(sbi); + fput(pipe); + } } static int autofs4_getpath(struct autofs_sb_info *sbi, @@ -171,7 +194,7 @@ static int autofs4_getpath(struct autofs for (tmp = dentry ; tmp != root ; tmp = tmp->d_parent) len += tmp->d_name.len + 1; - if (--len > NAME_MAX) { + if (!len || --len > NAME_MAX) { spin_unlock(&dcache_lock); return 0; } @@ -191,58 +214,55 @@ static int autofs4_getpath(struct autofs } static struct autofs_wait_queue * -autofs4_find_wait(struct autofs_sb_info *sbi, - char *name, unsigned int hash, unsigned int len) +autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr) { struct autofs_wait_queue *wq; for (wq = sbi->queues; wq; wq = wq->next) { - if (wq->hash == hash && - wq->len == len && - wq->name && !memcmp(wq->name, name, len)) + if (wq->name.hash == qstr->hash && + wq->name.len == qstr->len && + wq->name.name && + !memcmp(wq->name.name, qstr->name, qstr->len)) break; } return wq; } -int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, - enum autofs_notify notify) +/* + * Check if we have a valid request. + * Returns + * 1 if the request should continue. + * In this case we can return an autofs_wait_queue entry if one is + * found or NULL to idicate a new wait needs to be created. + * 0 or a negative errno if the request shouldn't continue. + */ +static int validate_request(struct autofs_wait_queue **wait, + struct autofs_sb_info *sbi, + struct qstr *qstr, + struct dentry*dentry, enum autofs_notify notify) { - struct autofs_info *ino; struct autofs_wait_queue *wq; - char *name; - unsigned int len = 0; - unsigned int hash = 0; - int status, type; - - /* In catatonic mode, we don't wait for nobody */ - if (sbi->catatonic) - return -ENOENT; - - name = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!name) - return -ENOMEM; + struct autofs_info *ino; - /* If this is a direct mount request create a dummy name */ - if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT)) - len = sprintf(name, "%p", dentry); - else { - len = autofs4_getpath(sbi, dentry, &name); - if (!len) { - kfree(name); - return -ENOENT; - } + /* Wait in progress, continue; */ + wq = autofs4_find_wait(sbi, qstr); + if (wq) { + *wait = wq; + return 1; } - hash = full_name_hash(name, len); - if (mutex_lock_interruptible(&sbi->wq_mutex)) { - kfree(name); - return -EINTR; - } + *wait = NULL; - wq = autofs4_find_wait(sbi, name, hash, len); + /* If we don't yet have any info this is a new request */ ino = autofs4_dentry_ino(dentry); - if (!wq && ino && notify == NFY_NONE) { + if (!ino) + return 1; + + /* + * If we've been asked to wait on an existing expire (NFY_NONE) + * but there is no wait in the queue ... + */ + if (notify == NFY_NONE) { /* * Either we've betean the pending expire to post it's * wait or it finished while we waited on the mutex. @@ -253,13 +273,14 @@ int autofs4_wait(struct autofs_sb_info * while (ino->flags & AUTOFS_INF_EXPIRING) { mutex_unlock(&sbi->wq_mutex); schedule_timeout_interruptible(HZ/10); - if (mutex_lock_interruptible(&sbi->wq_mutex)) { - kfree(name); + if (mutex_lock_interruptible(&sbi->wq_mutex)) return -EINTR; + + wq = autofs4_find_wait(sbi, qstr); + if (wq) { + *wait = wq; + return 1; } - wq = autofs4_find_wait(sbi, name, hash, len); - if (wq) - break; } /* @@ -267,18 +288,90 @@ int autofs4_wait(struct autofs_sb_info * * cases where we wait on NFY_NONE neither depend on the * return status of the wait. */ - if (!wq) { - kfree(name); - mutex_unlock(&sbi->wq_mutex); + return 0; + } + + /* + * If we've been asked to trigger a mount and the request + * completed while we waited on the mutex ... + */ + if (notify == NFY_MOUNT) { + /* + * If the dentry was successfully mounted while we slept + * on the wait queue mutex we can return success. If it + * isn't mounted (doesn't have submounts for the case of + * a multi-mount with no mount at it's base) we can + * continue on and create a new request. + */ + if (have_submounts(dentry)) return 0; + } + + return 1; +} + +int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, + enum autofs_notify notify) +{ + struct autofs_wait_queue *wq; + struct qstr qstr; + char *name; + int status, ret, type; + + /* In catatonic mode, we don't wait for nobody */ + if (sbi->catatonic) + return -ENOENT; + + if (!dentry->d_inode) { + /* + * A wait for a negative dentry is invalid for certain + * cases. A direct or offset mount "always" has its mount + * point directory created and so the request dentry must + * be positive or the map key doesn't exist. The situation + * is very similar for indirect mounts except only dentrys + * in the root of the autofs file system may be negative. + */ + if (autofs_type_trigger(sbi->type)) + return -ENOENT; + else if (!IS_ROOT(dentry->d_parent)) + return -ENOENT; + } + + name = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name) + return -ENOMEM; + + /* If this is a direct mount request create a dummy name */ + if (IS_ROOT(dentry) && autofs_type_trigger(sbi->type)) + qstr.len = sprintf(name, "%p", dentry); + else { + qstr.len = autofs4_getpath(sbi, dentry, &name); + if (!qstr.len) { + kfree(name); + return -ENOENT; } } + qstr.name = name; + qstr.hash = full_name_hash(name, qstr.len); + + if (mutex_lock_interruptible(&sbi->wq_mutex)) { + kfree(qstr.name); + return -EINTR; + } + + ret = validate_request(&wq, sbi, &qstr, dentry, notify); + if (ret <= 0) { + if (ret == 0) + mutex_unlock(&sbi->wq_mutex); + kfree(qstr.name); + return ret; + } if (!wq) { /* Create a new wait queue */ wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL); if (!wq) { - kfree(name); + kfree(qstr.name); mutex_unlock(&sbi->wq_mutex); return -ENOMEM; } @@ -289,9 +382,7 @@ int autofs4_wait(struct autofs_sb_info * wq->next = sbi->queues; sbi->queues = wq; init_waitqueue_head(&wq->queue); - wq->hash = hash; - wq->name = name; - wq->len = len; + memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->dev = autofs4_get_dev(sbi); wq->ino = autofs4_get_ino(sbi); wq->uid = current->uid; @@ -299,7 +390,7 @@ int autofs4_wait(struct autofs_sb_info * wq->pid = current->pid; wq->tgid = current->tgid; wq->status = -EINTR; /* Status return if interrupted */ - atomic_set(&wq->wait_ctr, 2); + wq->wait_ctr = 2; mutex_unlock(&sbi->wq_mutex); if (sbi->version < 5) { @@ -309,38 +400,35 @@ int autofs4_wait(struct autofs_sb_info * type = autofs_ptype_expire_multi; } else { if (notify == NFY_MOUNT) - type = (sbi->type & AUTOFS_TYPE_DIRECT) ? + type = autofs_type_trigger(sbi->type) ? autofs_ptype_missing_direct : autofs_ptype_missing_indirect; else - type = (sbi->type & AUTOFS_TYPE_DIRECT) ? + type = autofs_type_trigger(sbi->type) ? autofs_ptype_expire_direct : autofs_ptype_expire_indirect; } DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n", - (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify); + (unsigned long) wq->wait_queue_token, wq->name.len, + wq->name.name, notify); /* autofs4_notify_daemon() may block */ autofs4_notify_daemon(sbi, wq, type); } else { - atomic_inc(&wq->wait_ctr); + wq->wait_ctr++; mutex_unlock(&sbi->wq_mutex); - kfree(name); + kfree(qstr.name); DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d", - (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify); + (unsigned long) wq->wait_queue_token, wq->name.len, + wq->name.name, notify); } - /* wq->name is NULL if and only if the lock is already released */ - - if (sbi->catatonic) { - /* We might have slept, so check again for catatonic mode */ - wq->status = -ENOENT; - kfree(wq->name); - wq->name = NULL; - } - - if (wq->name) { + /* + * wq->name.name is NULL iff the lock is already released + * or the mount has been made catatonic. + */ + if (wq->name.name) { /* Block all but "shutdown" signals while waiting */ sigset_t oldset; unsigned long irqflags; @@ -351,7 +439,7 @@ int autofs4_wait(struct autofs_sb_info * recalc_sigpending(); spin_unlock_irqrestore(&current->sighand->siglock, irqflags); - wait_event_interruptible(wq->queue, wq->name == NULL); + wait_event_interruptible(wq->queue, wq->name.name == NULL); spin_lock_irqsave(&current->sighand->siglock, irqflags); current->blocked = oldset; @@ -363,9 +451,45 @@ int autofs4_wait(struct autofs_sb_info * status = wq->status; + /* + * For direct and offset mounts we need to track the requester's + * uid and gid in the dentry info struct. This is so it can be + * supplied, on request, by the misc device ioctl interface. + * This is needed during daemon resatart when reconnecting + * to existing, active, autofs mounts. The uid and gid (and + * related string values) may be used for macro substitution + * in autofs mount maps. + */ + if (!status) { + struct autofs_info *ino; + struct dentry *de = NULL; + + /* direct mount or browsable map */ + ino = autofs4_dentry_ino(dentry); + if (!ino) { + /* If not lookup actual dentry used */ + de = d_lookup(dentry->d_parent, &dentry->d_name); + if (de) + ino = autofs4_dentry_ino(de); + } + + /* Set mount requester */ + if (ino) { + spin_lock(&sbi->fs_lock); + ino->uid = wq->uid; + ino->gid = wq->gid; + spin_unlock(&sbi->fs_lock); + } + + if (de) + dput(de); + } + /* Are we the last process to need status? */ - if (atomic_dec_and_test(&wq->wait_ctr)) + mutex_lock(&sbi->wq_mutex); + if (!--wq->wait_ctr) kfree(wq); + mutex_unlock(&sbi->wq_mutex); return status; } @@ -387,16 +511,13 @@ int autofs4_wait_release(struct autofs_s } *wql = wq->next; /* Unlink from chain */ - mutex_unlock(&sbi->wq_mutex); - kfree(wq->name); - wq->name = NULL; /* Do not wait on this queue */ - + kfree(wq->name.name); + wq->name.name = NULL; /* Do not wait on this queue */ wq->status = status; - - if (atomic_dec_and_test(&wq->wait_ctr)) /* Is anyone still waiting for this guy? */ + wake_up_interruptible(&wq->queue); + if (!--wq->wait_ctr) kfree(wq); - else - wake_up_interruptible(&wq->queue); + mutex_unlock(&sbi->wq_mutex); return 0; } --- linux-2.6.22.orig/fs/autofs4/expire.c +++ linux-2.6.22/fs/autofs4/expire.c @@ -56,12 +56,25 @@ static int autofs4_mount_busy(struct vfs mntget(mnt); dget(dentry); - if (!autofs4_follow_mount(&mnt, &dentry)) + if (!follow_down(&mnt, &dentry)) goto done; - /* This is an autofs submount, we can't expire it */ - if (is_autofs4_dentry(dentry)) - goto done; + if (is_autofs4_dentry(dentry)) { + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + + /* This is an autofs submount, we can't expire it */ + if (autofs_type_indirect(sbi->type)) + goto done; + + /* + * Otherwise it's an offset mount and we need to check + * if we can umount its mount, if there is one. + */ + if (!d_mountpoint(dentry)) { + status = 0; + goto done; + } + } /* Update the expiry counter if fs is busy */ if (!may_umount_tree(mnt)) { @@ -73,8 +86,8 @@ static int autofs4_mount_busy(struct vfs status = 0; done: DPRINTK("returning = %d", status); - mntput(mnt); dput(dentry); + mntput(mnt); return status; } @@ -244,10 +257,10 @@ cont: } /* Check if we can expire a direct mount (possibly a tree) */ -static struct dentry *autofs4_expire_direct(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - int how) +struct dentry *autofs4_expire_direct(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + int how) { unsigned long timeout; struct dentry *root = dget(sb->s_root); @@ -259,13 +272,15 @@ static struct dentry *autofs4_expire_dir now = jiffies; timeout = sbi->exp_timeout; - /* Lock the tree as we must expire as a whole */ spin_lock(&sbi->fs_lock); if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { struct autofs_info *ino = autofs4_dentry_ino(root); - - /* Set this flag early to catch sys_chdir and the like */ + if (d_mountpoint(root)) { + ino->flags |= AUTOFS_INF_MOUNTPOINT; + root->d_mounted--; + } ino->flags |= AUTOFS_INF_EXPIRING; + init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return root; } @@ -281,10 +296,10 @@ static struct dentry *autofs4_expire_dir * - it is unused by any user process * - it has been unused for exp_timeout time */ -static struct dentry *autofs4_expire_indirect(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - int how) +struct dentry *autofs4_expire_indirect(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + int how) { unsigned long timeout; struct dentry *root = sb->s_root; @@ -292,6 +307,8 @@ static struct dentry *autofs4_expire_ind struct list_head *next; int do_now = how & AUTOFS_EXP_IMMEDIATE; int exp_leaves = how & AUTOFS_EXP_LEAVES; + struct autofs_info *ino; + unsigned int ino_count; if (!root) return NULL; @@ -316,6 +333,9 @@ static struct dentry *autofs4_expire_ind dentry = dget(dentry); spin_unlock(&dcache_lock); + spin_lock(&sbi->fs_lock); + ino = autofs4_dentry_ino(dentry); + /* * Case 1: (i) indirect mount or top level pseudo direct mount * (autofs-4.1). @@ -326,6 +346,11 @@ static struct dentry *autofs4_expire_ind DPRINTK("checking mountpoint %p %.*s", dentry, (int)dentry->d_name.len, dentry->d_name.name); + /* Path walk currently on this dentry? */ + ino_count = atomic_read(&ino->count) + 2; + if (atomic_read(&dentry->d_count) > ino_count) + goto next; + /* Can we umount this guy */ if (autofs4_mount_busy(mnt, dentry)) goto next; @@ -333,7 +358,7 @@ static struct dentry *autofs4_expire_ind /* Can we expire this guy */ if (autofs4_can_expire(dentry, timeout, do_now)) { expired = dentry; - break; + goto found; } goto next; } @@ -343,46 +368,80 @@ static struct dentry *autofs4_expire_ind /* Case 2: tree mount, expire iff entire tree is not busy */ if (!exp_leaves) { - /* Lock the tree as we must expire as a whole */ - spin_lock(&sbi->fs_lock); - if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) { - struct autofs_info *inf = autofs4_dentry_ino(dentry); + /* Path walk currently on this dentry? */ + ino_count = atomic_read(&ino->count) + 1; + if (atomic_read(&dentry->d_count) > ino_count) + goto next; - /* Set this flag early to catch sys_chdir and the like */ - inf->flags |= AUTOFS_INF_EXPIRING; - spin_unlock(&sbi->fs_lock); + if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) { expired = dentry; - break; + goto found; } - spin_unlock(&sbi->fs_lock); /* * Case 3: pseudo direct mount, expire individual leaves * (autofs-4.1). */ } else { + /* Path walk currently on this dentry? */ + ino_count = atomic_read(&ino->count) + 1; + if (atomic_read(&dentry->d_count) > ino_count) + goto next; + expired = autofs4_check_leaves(mnt, dentry, timeout, do_now); if (expired) { dput(dentry); - break; + goto found; } } next: + spin_unlock(&sbi->fs_lock); dput(dentry); spin_lock(&dcache_lock); next = next->next; } + spin_unlock(&dcache_lock); + return NULL; - if (expired) { - DPRINTK("returning %p %.*s", - expired, (int)expired->d_name.len, expired->d_name.name); - spin_lock(&dcache_lock); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); - spin_unlock(&dcache_lock); - return expired; - } +found: + DPRINTK("returning %p %.*s", + expired, (int)expired->d_name.len, expired->d_name.name); + ino = autofs4_dentry_ino(expired); + ino->flags |= AUTOFS_INF_EXPIRING; + init_completion(&ino->expire_complete); + spin_unlock(&sbi->fs_lock); + spin_lock(&dcache_lock); + list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); spin_unlock(&dcache_lock); + return expired; +} - return NULL; +int autofs4_expire_wait(struct dentry *dentry) +{ + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + int status; + + /* Block on any pending expire */ + spin_lock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_EXPIRING) { + spin_unlock(&sbi->fs_lock); + + DPRINTK("waiting for expire %p name=%.*s", + dentry, dentry->d_name.len, dentry->d_name.name); + + status = autofs4_wait(sbi, dentry, NFY_NONE); + wait_for_completion(&ino->expire_complete); + + DPRINTK("expire done status=%d", status); + + if (d_unhashed(dentry)) + return -EAGAIN; + + return status; + } + spin_unlock(&sbi->fs_lock); + + return 0; } /* Perform an expiry operation */ @@ -392,7 +451,9 @@ int autofs4_expire_run(struct super_bloc struct autofs_packet_expire __user *pkt_p) { struct autofs_packet_expire pkt; + struct autofs_info *ino; struct dentry *dentry; + int ret = 0; memset(&pkt,0,sizeof pkt); @@ -408,39 +469,59 @@ int autofs4_expire_run(struct super_bloc dput(dentry); if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) ) - return -EFAULT; + ret = -EFAULT; - return 0; + spin_lock(&sbi->fs_lock); + ino = autofs4_dentry_ino(dentry); + ino->flags &= ~AUTOFS_INF_EXPIRING; + complete_all(&ino->expire_complete); + spin_unlock(&sbi->fs_lock); + + return ret; } -/* Call repeatedly until it returns -EAGAIN, meaning there's nothing - more to be done */ -int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt, - struct autofs_sb_info *sbi, int __user *arg) +int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int when) { struct dentry *dentry; int ret = -EAGAIN; - int do_now = 0; - if (arg && get_user(do_now, arg)) - return -EFAULT; - - if (sbi->type & AUTOFS_TYPE_DIRECT) - dentry = autofs4_expire_direct(sb, mnt, sbi, do_now); + if (autofs_type_trigger(sbi->type)) + dentry = autofs4_expire_direct(sb, mnt, sbi, when); else - dentry = autofs4_expire_indirect(sb, mnt, sbi, do_now); + dentry = autofs4_expire_indirect(sb, mnt, sbi, when); if (dentry) { struct autofs_info *ino = autofs4_dentry_ino(dentry); /* This is synchronous because it makes the daemon a little easier */ - ino->flags |= AUTOFS_INF_EXPIRING; ret = autofs4_wait(sbi, dentry, NFY_EXPIRE); + + spin_lock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_MOUNTPOINT) { + sb->s_root->d_mounted++; + ino->flags &= ~AUTOFS_INF_MOUNTPOINT; + } ino->flags &= ~AUTOFS_INF_EXPIRING; + complete_all(&ino->expire_complete); + spin_unlock(&sbi->fs_lock); dput(dentry); } return ret; } +/* Call repeatedly until it returns -EAGAIN, meaning there's nothing + more to be done */ +int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int __user *arg) +{ + int do_now = 0; + + if (arg && get_user(do_now, arg)) + return -EFAULT; + + return autofs4_do_expire_multi(sb, mnt, sbi, do_now); +} + --- linux-2.6.22.orig/fs/autofs4/autofs_i.h +++ linux-2.6.22/fs/autofs4/autofs_i.h @@ -14,6 +14,7 @@ /* Internal header file for autofs */ #include <linux/auto_fs4.h> +#include <linux/auto_dev-ioctl.h> #include <linux/mutex.h> #include <linux/list.h> @@ -21,6 +22,9 @@ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY #define AUTOFS_IOC_COUNT 32 +#define AUTOFS_DEV_IOCTL_IOC_FIRST (AUTOFS_DEV_IOCTL_VERSION) +#define AUTOFS_DEV_IOCTL_IOC_COUNT (AUTOFS_IOC_COUNT - 11) + #include <linux/kernel.h> #include <linux/slab.h> #include <linux/time.h> @@ -35,11 +39,27 @@ /* #define DEBUG */ #ifdef DEBUG -#define DPRINTK(fmt,args...) do { printk(KERN_DEBUG "pid %d: %s: " fmt "\n" , current->pid , __FUNCTION__ , ##args); } while(0) +#define DPRINTK(fmt, args...) \ +do { \ + printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \ + current->pid, __FUNCTION__, ##args); \ +} while (0) #else -#define DPRINTK(fmt,args...) do {} while(0) +#define DPRINTK(fmt, args...) do {} while (0) #endif +#define AUTOFS_WARN(fmt, args...) \ +do { \ + printk(KERN_WARNING "pid %d: %s: " fmt "\n", \ + current->pid, __FUNCTION__, ##args); \ +} while (0) + +#define AUTOFS_ERROR(fmt, args...) \ +do { \ + printk(KERN_ERR "pid %d: %s: " fmt "\n", \ + current->pid, __FUNCTION__, ##args); \ +} while (0) + /* Unified info structure. This is pointed to by both the dentry and inode structures. Each file in the filesystem has an instance of this structure. It holds a reference to the dentry, so dentries are never @@ -52,12 +72,18 @@ struct autofs_info { int flags; - struct list_head rehash; + struct completion expire_complete; + + struct list_head active; + struct list_head expiring; struct autofs_sb_info *sbi; unsigned long last_used; atomic_t count; + uid_t uid; + gid_t gid; + mode_t mode; size_t size; @@ -68,15 +94,14 @@ struct autofs_info { }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry is in the process of expiring */ +#define AUTOFS_INF_MOUNTPOINT (1<<1) /* mountpoint status for direct expire */ struct autofs_wait_queue { wait_queue_head_t queue; struct autofs_wait_queue *next; autofs_wqt_t wait_queue_token; /* We use the following to see what we are waiting for */ - unsigned int hash; - unsigned int len; - char *name; + struct qstr name; u32 dev; u64 ino; uid_t uid; @@ -85,15 +110,11 @@ struct autofs_wait_queue { pid_t tgid; /* This is for status reporting upon return */ int status; - atomic_t wait_ctr; + unsigned int wait_ctr; }; #define AUTOFS_SBI_MAGIC 0x6d4a556d -#define AUTOFS_TYPE_INDIRECT 0x0001 -#define AUTOFS_TYPE_DIRECT 0x0002 -#define AUTOFS_TYPE_OFFSET 0x0004 - struct autofs_sb_info { u32 magic; int pipefd; @@ -112,8 +133,9 @@ struct autofs_sb_info { struct mutex wq_mutex; spinlock_t fs_lock; struct autofs_wait_queue *queues; /* Wait queue pointer */ - spinlock_t rehash_lock; - struct list_head rehash_list; + spinlock_t lookup_lock; + struct list_head active_list; + struct list_head expiring_list; }; static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb) @@ -138,18 +160,14 @@ static inline int autofs4_oz_mode(struct static inline int autofs4_ispending(struct dentry *dentry) { struct autofs_info *inf = autofs4_dentry_ino(dentry); - int pending = 0; if (dentry->d_flags & DCACHE_AUTOFS_PENDING) return 1; - if (inf) { - spin_lock(&inf->sbi->fs_lock); - pending = inf->flags & AUTOFS_INF_EXPIRING; - spin_unlock(&inf->sbi->fs_lock); - } + if (inf->flags & AUTOFS_INF_EXPIRING) + return 1; - return pending; + return 0; } static inline void autofs4_copy_atime(struct file *src, struct file *dst) @@ -164,11 +182,25 @@ void autofs4_free_ino(struct autofs_info /* Expiration */ int is_autofs4_dentry(struct dentry *); +int autofs4_expire_wait(struct dentry *dentry); int autofs4_expire_run(struct super_block *, struct vfsmount *, struct autofs_sb_info *, struct autofs_packet_expire __user *); +int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int when); int autofs4_expire_multi(struct super_block *, struct vfsmount *, struct autofs_sb_info *, int __user *); +struct dentry *autofs4_expire_direct(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, int how); +struct dentry *autofs4_expire_indirect(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, int how); + +/* Device node initialization */ + +int autofs_dev_ioctl_init(void); +void autofs_dev_ioctl_exit(void); /* Operations structures */ --- linux-2.6.22.orig/fs/autofs4/inode.c +++ linux-2.6.22/fs/autofs4/inode.c @@ -24,8 +24,10 @@ static void ino_lnkfree(struct autofs_info *ino) { - kfree(ino->u.symlink); - ino->u.symlink = NULL; + if (ino->u.symlink) { + kfree(ino->u.symlink); + ino->u.symlink = NULL; + } } struct autofs_info *autofs4_init_ino(struct autofs_info *ino, @@ -41,16 +43,20 @@ struct autofs_info *autofs4_init_ino(str if (ino == NULL) return NULL; - ino->flags = 0; - ino->mode = mode; - ino->inode = NULL; - ino->dentry = NULL; - ino->size = 0; - - INIT_LIST_HEAD(&ino->rehash); + if (!reinit) { + ino->flags = 0; + ino->inode = NULL; + ino->dentry = NULL; + ino->size = 0; + INIT_LIST_HEAD(&ino->active); + INIT_LIST_HEAD(&ino->expiring); + atomic_set(&ino->count, 0); + } + ino->uid = 0; + ino->gid = 0; + ino->mode = mode; ino->last_used = jiffies; - atomic_set(&ino->count, 0); ino->sbi = sbi; @@ -159,8 +165,8 @@ void autofs4_kill_sb(struct super_block if (!sbi) goto out_kill_sb; - if (!sbi->catatonic) - autofs4_catatonic_mode(sbi); /* Free wait queues, close pipe */ + /* Free wait queues, close pipe */ + autofs4_catatonic_mode(sbi); /* Clean up and release dangling references */ autofs4_force_release(sbi); @@ -186,9 +192,9 @@ static int autofs4_show_options(struct s seq_printf(m, ",minproto=%d", sbi->min_proto); seq_printf(m, ",maxproto=%d", sbi->max_proto); - if (sbi->type & AUTOFS_TYPE_OFFSET) + if (autofs_type_offset(sbi->type)) seq_printf(m, ",offset"); - else if (sbi->type & AUTOFS_TYPE_DIRECT) + else if (autofs_type_direct(sbi->type)) seq_printf(m, ",direct"); else seq_printf(m, ",indirect"); @@ -273,13 +279,13 @@ static int parse_options(char *options, *maxproto = option; break; case Opt_indirect: - *type = AUTOFS_TYPE_INDIRECT; + set_autofs_type_indirect(type); break; case Opt_direct: - *type = AUTOFS_TYPE_DIRECT; + set_autofs_type_direct(type); break; case Opt_offset: - *type = AUTOFS_TYPE_DIRECT | AUTOFS_TYPE_OFFSET; + set_autofs_type_offset(type); break; default: return 1; @@ -329,14 +335,15 @@ int autofs4_fill_super(struct super_bloc sbi->sb = s; sbi->version = 0; sbi->sub_version = 0; - sbi->type = 0; + set_autofs_type_indirect(&sbi->type); sbi->min_proto = 0; sbi->max_proto = 0; mutex_init(&sbi->wq_mutex); spin_lock_init(&sbi->fs_lock); sbi->queues = NULL; - spin_lock_init(&sbi->rehash_lock); - INIT_LIST_HEAD(&sbi->rehash_list); + spin_lock_init(&sbi->lookup_lock); + INIT_LIST_HEAD(&sbi->active_list); + INIT_LIST_HEAD(&sbi->expiring_list); s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = AUTOFS_SUPER_MAGIC; @@ -370,7 +377,7 @@ int autofs4_fill_super(struct super_bloc } root_inode->i_fop = &autofs4_root_operations; - root_inode->i_op = sbi->type & AUTOFS_TYPE_DIRECT ? + root_inode->i_op = autofs_type_trigger(sbi->type) ? &autofs4_direct_root_inode_operations : &autofs4_indirect_root_inode_operations; --- linux-2.6.22.orig/fs/compat_ioctl.c +++ linux-2.6.22/fs/compat_ioctl.c @@ -2998,8 +2998,6 @@ COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOVER) COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE) COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE_MULTI) COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOSUBVER) -COMPATIBLE_IOCTL(AUTOFS_IOC_ASKREGHOST) -COMPATIBLE_IOCTL(AUTOFS_IOC_TOGGLEREGHOST) COMPATIBLE_IOCTL(AUTOFS_IOC_ASKUMOUNT) /* Raw devices */ COMPATIBLE_IOCTL(RAW_SETBIND) --- linux-2.6.22.orig/include/linux/auto_fs4.h +++ linux-2.6.22/include/linux/auto_fs4.h @@ -23,12 +23,71 @@ #define AUTOFS_MIN_PROTO_VERSION 3 #define AUTOFS_MAX_PROTO_VERSION 5 -#define AUTOFS_PROTO_SUBVERSION 0 +#define AUTOFS_PROTO_SUBVERSION 1 /* Mask for expire behaviour */ #define AUTOFS_EXP_IMMEDIATE 1 #define AUTOFS_EXP_LEAVES 2 +#define AUTOFS_TYPE_ANY 0U +#define AUTOFS_TYPE_INDIRECT 1U +#define AUTOFS_TYPE_DIRECT 2U +#define AUTOFS_TYPE_OFFSET 4U + +static inline void set_autofs_type_indirect(unsigned int *type) +{ + *type = AUTOFS_TYPE_INDIRECT; + return; +} + +static inline unsigned int autofs_type_indirect(unsigned int type) +{ + return (type == AUTOFS_TYPE_INDIRECT); +} + +static inline void set_autofs_type_direct(unsigned int *type) +{ + *type = AUTOFS_TYPE_DIRECT; + return; +} + +static inline unsigned int autofs_type_direct(unsigned int type) +{ + return (type == AUTOFS_TYPE_DIRECT); +} + +static inline void set_autofs_type_offset(unsigned int *type) +{ + *type = AUTOFS_TYPE_OFFSET; + return; +} + +static inline unsigned int autofs_type_offset(unsigned int type) +{ + return (type == AUTOFS_TYPE_OFFSET); +} + +static inline unsigned int autofs_type_trigger(unsigned int type) +{ + return (type == AUTOFS_TYPE_DIRECT || type == AUTOFS_TYPE_OFFSET); +} + +/* + * This isn't really a type as we use it to say "no type set" to + * indicate we want to search for "any" mount in the + * autofs_dev_ioctl_ismountpoint() device ioctl function. + */ +static inline void set_autofs_type_any(unsigned int *type) +{ + *type = AUTOFS_TYPE_ANY; + return; +} + +static inline unsigned int autofs_type_any(unsigned int type) +{ + return (type == AUTOFS_TYPE_ANY); +} + /* Daemon notification packet types */ enum autofs_notify { NFY_NONE, @@ -98,8 +157,6 @@ union autofs_v5_packet_union { #define AUTOFS_IOC_EXPIRE_INDIRECT AUTOFS_IOC_EXPIRE_MULTI #define AUTOFS_IOC_EXPIRE_DIRECT AUTOFS_IOC_EXPIRE_MULTI #define AUTOFS_IOC_PROTOSUBVER _IOR(0x93,0x67,int) -#define AUTOFS_IOC_ASKREGHOST _IOR(0x93,0x68,int) -#define AUTOFS_IOC_TOGGLEREGHOST _IOR(0x93,0x69,int) #define AUTOFS_IOC_ASKUMOUNT _IOR(0x93,0x70,int) --- /dev/null +++ linux-2.6.22/Documentation/filesystems/autofs4-mount-control.txt @@ -0,0 +1,414 @@ + +Miscellaneous Device control operations for the autofs4 kernel module +==================================================================== + +The problem +=========== + +There is a problem with active restarts in autofs (that is to say +restarting autofs when there are busy mounts). + +During normal operation autofs uses a file descriptor opened on the +directory that is being managed in order to be able to issue control +operations. Using a file descriptor gives ioctl operations access to +autofs specific information stored in the super block. The operations +are things such as setting an autofs mount catatonic, setting the +expire timeout and requesting expire checks. As is explained below, +certain types of autofs triggered mounts can end up covering an autofs +mount itself which prevents us being able to use open(2) to obtain a +file descriptor for these operations if we don't already have one open. + +Currently autofs uses "umount -l" (lazy umount) to clear active mounts +at restart. While using lazy umount works for most cases, anything that +needs to walk back up the mount tree to construct a path, such as +getcwd(2) and the proc file system /proc/<pid>/cwd, no longer works +because the point from which the path is constructed has been detached +from the mount tree. + +The actual problem with autofs is that it can't reconnect to existing +mounts. Immediately one thinks of just adding the ability to remount +autofs file systems would solve it, but alas, that can't work. This is +because autofs direct mounts and the implementation of "on demand mount +and expire" of nested mount trees have the file system mounted directly +on top of the mount trigger directory dentry. + +For example, there are two types of automount maps, direct (in the kernel +module source you will see a third type called an offset, which is just +a direct mount in disguise) and indirect. + +Here is a master map with direct and indirect map entries: + +/- /etc/auto.direct +/test /etc/auto.indirect + +and the corresponding map files: + +/etc/auto.direct: + +/automount/dparse/g6 budgie:/autofs/export1 +/automount/dparse/g1 shark:/autofs/export1 +and so on. + +/etc/auto.indirect: + +g1 shark:/autofs/export1 +g6 budgie:/autofs/export1 +and so on. + +For the above indirect map an autofs file system is mounted on /test and +mounts are triggered for each sub-directory key by the inode lookup +operation. So we see a mount of shark:/autofs/export1 on /test/g1, for +example. + +The way that direct mounts are handled is by making an autofs mount on +each full path, such as /automount/dparse/g1, and using it as a mount +trigger. So when we walk on the path we mount shark:/autofs/export1 "on +top of this mount point". Since these are always directories we can +use the follow_link inode operation to trigger the mount. + +But, each entry in direct and indirect maps can have offsets (making +them multi-mount map entries). + +For example, an indirect mount map entry could also be: + +g1 \ + / shark:/autofs/export5/testing/test \ + /s1 shark:/autofs/export/testing/test/s1 \ + /s2 shark:/autofs/export5/testing/test/s2 \ + /s1/ss1 shark:/autofs/export1 \ + /s2/ss2 shark:/autofs/export2 + +and a similarly a direct mount map entry could also be: + +/automount/dparse/g1 \ + / shark:/autofs/export5/testing/test \ + /s1 shark:/autofs/export/testing/test/s1 \ + /s2 shark:/autofs/export5/testing/test/s2 \ + /s1/ss1 shark:/autofs/export2 \ + /s2/ss2 shark:/autofs/export2 + +One of the issues with version 4 of autofs was that, when mounting an +entry with a large number of offsets, possibly with nesting, we needed +to mount and umount all of the offsets as a single unit. Not really a +problem, except for people with a large number of offsets in map entries. +This mechanism is used for the well known "hosts" map and we have seen +cases (in 2.4) where the available number of mounts are exhausted or +where the number of privileged ports available is exhausted. + +In version 5 we mount only as we go down the tree of offsets and +similarly for expiring them which resolves the above problem. There is +somewhat more detail to the implementation but it isn't needed for the +sake of the problem explanation. The one important detail is that these +offsets are implemented using the same mechanism as the direct mounts +above and so the mount points can be covered by a mount. + +The current autofs implementation uses an ioctl file descriptor opened +on the mount point for control operations. The references held by the +descriptor are accounted for in checks made to determine if a mount is +in use and is also used to access autofs file system information held +in the mount super block. So the use of a file handle needs to be +retained. + + +The Solution +============ + +To be able to restart autofs leaving existing direct, indirect and +offset mounts in place we need to be able to obtain a file handle +for these potentially covered autofs mount points. Rather than just +implement an isolated operation it was decided to re-implement the +existing ioctl interface and add new operations to provide this +functionality. + +In addition, to be able to reconstruct a mount tree that has busy mounts, +the uid and gid of the last user that triggered the mount needs to be +available because these can be used as macro substitution variables in +autofs maps. They are recorded at mount request time and an operation +has been added to retrieve them. + +Since we're re-implementing the control interface, a couple of other +problems with the existing interface have been addressed. First, when +a mount or expire operation completes a status is returned to the +kernel by either a "send ready" or a "send fail" operation. The +"send fail" operation of the ioctl interface could only ever send +ENOENT so the re-implementation allows user space to send an actual +status. Another expensive operation in user space, for those using +very large maps, is discovering if a mount is present. Usually this +involves scanning /proc/mounts and since it needs to be done quite +often it can introduce significant overhead when there are many entries +in the mount table. An operation to lookup the mount status of a mount +point dentry (covered or not) has also been added. + +Current kernel development policy recommends avoiding the use of the +ioctl mechanism in favor of systems such as Netlink. An implementation +using this system was attempted to evaluate its suitability and it was +found to be inadequate, in this case. The Generic Netlink system was +used for this as raw Netlink would lead to a significant increase in +complexity. There's no question that the Generic Netlink system is an +elegant solution for common case ioctl functions but it's not a complete +replacement probably because it's primary purpose in life is to be a +message bus implementation rather than specifically an ioctl replacement. +While it would be possible to work around this there is one concern +that lead to the decision to not use it. This is that the autofs +expire in the daemon has become far to complex because umount +candidates are enumerated, almost for no other reason than to "count" +the number of times to call the expire ioctl. This involves scanning +the mount table which has proved to be a big overhead for users with +large maps. The best way to improve this is try and get back to the +way the expire was done long ago. That is, when an expire request is +issued for a mount (file handle) we should continually call back to +the daemon until we can't umount any more mounts, then return the +appropriate status to the daemon. At the moment we just expire one +mount at a time. A Generic Netlink implementation would exclude this +possibility for future development due to the requirements of the +message bus architecture. + + +autofs4 Miscellaneous Device mount control interface +==================================================== + +The control interface is opening a device node, typically /dev/autofs. + +All the ioctls use a common structure to pass the needed parameter +information and return operation results: + +struct autofs_dev_ioctl { + __u32 ver_major; + __u32 ver_minor; + __u32 size; /* total size of data passed in + * including this struct */ + __s32 ioctlfd; /* automount command fd */ + + /* Command parameters */ + + union { + struct args_protover protover; + struct args_protosubver protosubver; + struct args_openmount openmount; + struct args_ready ready; + struct args_fail fail; + struct args_setpipefd setpipefd; + struct args_timeout timeout; + struct args_requester requester; + struct args_expire expire; + struct args_askumount askumount; + struct args_ismountpoint ismountpoint; + }; + + char path[0]; +}; + +The ioctlfd field is a mount point file descriptor of an autofs mount +point. It is returned by the open call and is used by all calls except +the check for whether a given path is a mount point, where it may +optionally be used to check a specific mount corresponding to a given +mount point file descriptor, and when requesting the uid and gid of the +last successful mount on a directory within the autofs file system. + +The anonymous union is used to communicate parameters and results of calls +made as described below. + +The path field is used to pass a path where it is needed and the size field +is used account for the increased structure length when translating the +structure sent from user space. + +This structure can be initialized before setting specific fields by using +the void function call init_autofs_dev_ioctl(struct autofs_dev_ioctl *). + +All of the ioctls perform a copy of this structure from user space to +kernel space and return -EINVAL if the size parameter is smaller than +the structure size itself, -ENOMEM if the kernel memory allocation fails +or -EFAULT if the copy itself fails. Other checks include a version check +of the compiled in user space version against the module version and a +mismatch results in a -EINVAL return. If the size field is greater than +the structure size then a path is assumed to be present and is checked to +ensure it begins with a "/" and is NULL terminated, otherwise -EINVAL is +returned. Following these checks, for all ioctl commands except +AUTOFS_DEV_IOCTL_VERSION_CMD, AUTOFS_DEV_IOCTL_OPENMOUNT_CMD and +AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD the ioctlfd is validated and if it is +not a valid descriptor or doesn't correspond to an autofs mount point +an error of -EBADF, -ENOTTY or -EINVAL (not an autofs descriptor) is +returned. + + +The ioctls +========== + +An example of an implementation which uses this interface can be seen +in autofs version 5.0.4 and later in file lib/dev-ioctl-lib.c of the +distribution tar available for download from kernel.org in directory +/pub/linux/daemons/autofs/v5. + +The device node ioctl operations implemented by this interface are: + + +AUTOFS_DEV_IOCTL_VERSION +------------------------ + +Get the major and minor version of the autofs4 device ioctl kernel module +implementation. It requires an initialized struct autofs_dev_ioctl as an +input parameter and sets the version information in the passed in structure. +It returns 0 on success or the error -EINVAL if a version mismatch is +detected. + + +AUTOFS_DEV_IOCTL_PROTOVER_CMD and AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD +------------------------------------------------------------------ + +Get the major and minor version of the autofs4 protocol version understood +by loaded module. This call requires an initialized struct autofs_dev_ioctl +with the ioctlfd field set to a valid autofs mount point descriptor +and sets the requested version number in structure field protover.version +and ptotosubver.sub_version respectively. These commands return 0 on +success or one of the negative error codes if validation fails. + + +AUTOFS_DEV_IOCTL_OPENMOUNT_CMD and AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD +------------------------------------------------------------------ + +Obtain and release a file descriptor for an autofs managed mount point +path. The open call requires an initialized struct autofs_dev_ioctl with +the the path field set and the size field adjusted appropriately as well +as the openmount.devid field set to the device number of the autofs mount. +The device number of an autofs mounted filesystem can be obtained by using +the AUTOFS_DEV_IOCTL_ISMOUNTPOINT ioctl function by providing the path +and autofs mount type, as described below. The close call requires an +initialized struct autofs_dev_ioct with the ioctlfd field set to the +descriptor obtained from the open call. The release of the file descriptor +can also be done with close(2) so any open descriptors will also be +closed at process exit. The close call is included in the implemented +operations largely for completeness and to provide for a consistent +user space implementation. + + +AUTOFS_DEV_IOCTL_READY_CMD and AUTOFS_DEV_IOCTL_FAIL_CMD +-------------------------------------------------------- + +Return mount and expire result status from user space to the kernel. +Both of these calls require an initialized struct autofs_dev_ioctl +with the ioctlfd field set to the descriptor obtained from the open +call and the ready.token or fail.token field set to the wait queue +token number, received by user space in the foregoing mount or expire +request. The fail.status field is set to the status to be returned when +sending a failure notification with AUTOFS_DEV_IOCTL_FAIL_CMD. + + +AUTOFS_DEV_IOCTL_SETPIPEFD_CMD +------------------------------ + +Set the pipe file descriptor used for kernel communication to the daemon. +Normally this is set at mount time using an option but when reconnecting +to a existing mount we need to use this to tell the autofs mount about +the new kernel pipe descriptor. In order to protect mounts against +incorrectly setting the pipe descriptor we also require that the autofs +mount be catatonic (see next call). + +The call requires an initialized struct autofs_dev_ioctl with the +ioctlfd field set to the descriptor obtained from the open call and +the setpipefd.pipefd field set to descriptor of the pipe. On success +the call also sets the process group id used to identify the controlling +process (eg. the owning automount(8) daemon) to the process group of +the caller. + + +AUTOFS_DEV_IOCTL_CATATONIC_CMD +------------------------------ + +Make the autofs mount point catatonic. The autofs mount will no longer +issue mount requests, the kernel communication pipe descriptor is released +and any remaining waits in the queue released. + +The call requires an initialized struct autofs_dev_ioctl with the +ioctlfd field set to the descriptor obtained from the open call. + + +AUTOFS_DEV_IOCTL_TIMEOUT_CMD +---------------------------- + +Set the expire timeout for mounts withing an autofs mount point. + +The call requires an initialized struct autofs_dev_ioctl with the +ioctlfd field set to the descriptor obtained from the open call. +The timeout.timeout field is set to the desired timeout and this +field is set to the value of the value of the current timeout of +the mount upon successful completion. + + +AUTOFS_DEV_IOCTL_REQUESTER_CMD +------------------------------ + +Return the uid and gid of the last process to successfully trigger a the +mount on the given path dentry. + +The call requires an initialized struct autofs_dev_ioctl with the path +field set to the mount point in question and the size field adjusted +appropriately as well as the ioctlfd field set to the descriptor obtained +from the open call. Upon return the struct fields requester.uid and +requester.gid contain the uid and gid respectively. + +When reconstructing an autofs mount tree with active mounts we need to +re-connect to mounts that may have used the original process uid and +gid (or string variations of them) for mount lookups within the map entry. +This call provides the ability to obtain this uid and gid so they may be +used by user space for the mount map lookups. + + +AUTOFS_DEV_IOCTL_EXPIRE_CMD +--------------------------- + +Issue an expire request to the kernel for an autofs mount. Typically +this ioctl is called until no further expire candidates are found. + +The call requires an initialized struct autofs_dev_ioctl with the +ioctlfd field set to the descriptor obtained from the open call. In +addition an immediate expire, independent of the mount timeout, can be +requested by setting the expire.how field to 1. If no expire candidates +can be found the ioctl returns -1 with errno set to EAGAIN. + +This call causes the kernel module to check the mount corresponding +to the given ioctlfd for mounts that can be expired, issues an expire +request back to the daemon and waits for completion. + +AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD +------------------------------ + +Checks if an autofs mount point is in use. + +The call requires an initialized struct autofs_dev_ioctl with the +ioctlfd field set to the descriptor obtained from the open call and +it returns the result in the askumount.may_umount field, 1 for busy +and 0 otherwise. + + +AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD +--------------------------------- + +Check if the given path is a mountpoint. + +The call requires an initialized struct autofs_dev_ioctl. There are two +possible variations. Both use the path field set to the path of the mount +point to check and the size field must be adjusted appropriately. One uses +the ioctlfd field to identify a specific mount point to check while the +other variation uses the path and optionaly the ismountpoint.in.type +field set to an autofs mount type. The call returns 1 if this is a mount +point and sets the ismountpoint.out.devid field to the device number of +the mount and the ismountpoint.out.magic field to the relevant super +block magic number (described below) or 0 if it isn't a mountpoint. In +both cases the the device number (as returned by new_encode_dev()) is +returned in the ismountpoint.out.devid field. + +If supplied with a file descriptor we're looking for a specific mount, +not necessarily at the top of the mounted stack. In this case the path +the descriptor corresponds to is considered a mountpoint if it is itself +a mountpoint or contains a mount, such as a multi-mount without a root +mount. In this case we return 1 if the descriptor corresponds to a mount +point and and also returns the super magic of the covering mount if there +is one or 0 if it isn't a mountpoint. + +If a path is supplied (and the ioctlfd field is set to -1) then the path +is looked up and is checked to see if it is the root of a mount. If a +type is also given we are looking for a particular autofs mount and if +a match isn't found a fail is returned. If the the located path is the +root of a mount 1 is returned along with the super magic of the mount +or 0 otherwise. + --- linux-2.6.22.orig/fs/autofs4/Makefile +++ linux-2.6.22/fs/autofs4/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_AUTOFS4_FS) += autofs4.o -autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o +autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o --- /dev/null +++ linux-2.6.22/fs/autofs4/dev-ioctl.c @@ -0,0 +1,840 @@ +/* + * Copyright 2008 Red Hat, Inc. All rights reserved. + * Copyright 2008 Ian Kent <raven@themaw.net> + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + */ + +#include <linux/module.h> +#include <linux/vmalloc.h> +#include <linux/miscdevice.h> +#include <linux/init.h> +#include <linux/wait.h> +#include <linux/namei.h> +#include <linux/fcntl.h> +#include <linux/file.h> +#include <linux/sched.h> +#include <linux/compat.h> +#include <linux/syscalls.h> +#include <linux/smp_lock.h> +#include <linux/magic.h> +#include <linux/dcache.h> +#include <linux/uaccess.h> + +#include "autofs_i.h" + +/* + * This module implements an interface for routing autofs ioctl control + * commands via a miscellaneous device file. + * + * The alternate interface is needed because we need to be able open + * an ioctl file descriptor on an autofs mount that may be covered by + * another mount. This situation arises when starting automount(8) + * or other user space daemon which uses direct mounts or offset + * mounts (used for autofs lazy mount/umount of nested mount trees), + * which have been left busy at at service shutdown. + */ + +#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) + +typedef int (*ioctl_fn)(struct file *, +struct autofs_sb_info *, struct autofs_dev_ioctl *); + +static int check_name(const char *name) +{ + if (!strchr(name, '/')) + return -EINVAL; + return 0; +} + +/* + * Check a string doesn't overrun the chunk of + * memory we copied from user land. + */ +static int invalid_str(char *str, void *end) +{ + while ((void *) str <= end) + if (!*str++) + return 0; + return -EINVAL; +} + +/* + * Check that the user compiled against correct version of autofs + * misc device code. + * + * As well as checking the version compatibility this always copies + * the kernel interface version out. + */ +static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) +{ + int err = 0; + + if ((AUTOFS_DEV_IOCTL_VERSION_MAJOR != param->ver_major) || + (AUTOFS_DEV_IOCTL_VERSION_MINOR < param->ver_minor)) { + AUTOFS_WARN("ioctl control interface version mismatch: " + "kernel(%u.%u), user(%u.%u), cmd(%d)", + AUTOFS_DEV_IOCTL_VERSION_MAJOR, + AUTOFS_DEV_IOCTL_VERSION_MINOR, + param->ver_major, param->ver_minor, cmd); + err = -EINVAL; + } + + /* Fill in the kernel version. */ + param->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; + param->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; + + return err; +} + +/* + * Copy parameter control struct, including a possible path allocated + * at the end of the struct. + */ +static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in) +{ + struct autofs_dev_ioctl tmp, *ads; + + if (copy_from_user(&tmp, in, sizeof(tmp))) + return ERR_PTR(-EFAULT); + + if (tmp.size < sizeof(tmp)) + return ERR_PTR(-EINVAL); + + ads = kmalloc(tmp.size, GFP_KERNEL); + if (!ads) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(ads, in, tmp.size)) { + kfree(ads); + return ERR_PTR(-EFAULT); + } + + return ads; +} + +static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) +{ + kfree(param); + return; +} + +/* + * Check sanity of parameter control fields and if a path is present + * check that it is terminated and contains at least one "/". + */ +static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) +{ + int err; + + if ((err = check_dev_ioctl_version(cmd, param))) { + AUTOFS_WARN("invalid device control module version " + "supplied for cmd(0x%08x)", cmd); + goto out; + } + + if (param->size > sizeof(*param)) { + err = invalid_str(param->path, + (void *) ((size_t) param + param->size)); + if (err) { + AUTOFS_WARN( + "path string terminator missing for cmd(0x%08x)", + cmd); + goto out; + } + + err = check_name(param->path); + if (err) { + AUTOFS_WARN("invalid path supplied for cmd(0x%08x)", + cmd); + goto out; + } + } + + err = 0; +out: + return err; +} + +/* + * Get the autofs super block info struct from the file opened on + * the autofs mount point. + */ +static struct autofs_sb_info *autofs_dev_ioctl_sbi(struct file *f) +{ + struct autofs_sb_info *sbi = NULL; + struct inode *inode; + + if (f) { + inode = f->f_path.dentry->d_inode; + sbi = autofs4_sbi(inode->i_sb); + } + return sbi; +} + +/* Return autofs module protocol version */ +static int autofs_dev_ioctl_protover(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + param->protover.version = sbi->version; + return 0; +} + +/* Return autofs module protocol sub version */ +static int autofs_dev_ioctl_protosubver(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + param->protosubver.sub_version = sbi->sub_version; + return 0; +} + +/* + * Walk down the mount stack looking for an autofs mount that + * has the requested device number (aka. new_encode_dev(sb->s_dev). + */ +static int autofs_dev_ioctl_find_super(struct nameidata *nd, dev_t devno) +{ + struct dentry *dentry; + struct inode *inode; + struct super_block *sb; + dev_t s_dev; + unsigned int err; + + err = -ENOENT; + + /* Lookup the dentry name at the base of our mount point */ + dentry = d_lookup(nd->dentry, &nd->last); + if (!dentry) + goto out; + + dput(nd->dentry); + nd->dentry = dentry; + + /* And follow the mount stack looking for our autofs mount */ + while (follow_down(&nd->mnt, &nd->dentry)) { + inode = nd->dentry->d_inode; + if (!inode) + break; + + sb = inode->i_sb; + s_dev = new_encode_dev(sb->s_dev); + if (devno == s_dev) { + if (sb->s_magic == AUTOFS_SUPER_MAGIC) { + err = 0; + break; + } + } + } +out: + return err; +} + +/* + * Walk down the mount stack looking for an autofs mount that + * has the requested mount type (ie. indirect, direct or offset). + */ +static int autofs_dev_ioctl_find_sbi_type(struct nameidata *nd, unsigned int type) +{ + struct dentry *dentry; + struct autofs_info *ino; + unsigned int err; + + err = -ENOENT; + + /* Lookup the dentry name at the base of our mount point */ + dentry = d_lookup(nd->dentry, &nd->last); + if (!dentry) + goto out; + + dput(nd->dentry); + nd->dentry = dentry; + + /* And follow the mount stack looking for our autofs mount */ + while (follow_down(&nd->mnt, &nd->dentry)) { + ino = autofs4_dentry_ino(nd->dentry); + if (ino && ino->sbi->type & type) { + err = 0; + break; + } + } +out: + return err; +} + +static void autofs_dev_ioctl_fd_install(unsigned int fd, struct file *file) +{ + struct files_struct *files = current->files; + struct fdtable *fdt; + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + BUG_ON(fdt->fd[fd] != NULL); + rcu_assign_pointer(fdt->fd[fd], file); + FD_SET(fd, fdt->close_on_exec); + spin_unlock(&files->file_lock); +} + + +/* + * Open a file descriptor on the autofs mount point corresponding + * to the given path and device number (aka. new_encode_dev(sb->s_dev)). + */ +static int autofs_dev_ioctl_open_mountpoint(const char *path, dev_t devid) +{ + struct file *filp; + struct nameidata nd; + int err, fd; + + fd = get_unused_fd(); + if (likely(fd >= 0)) { + /* Get nameidata of the parent directory */ + err = path_lookup(path, LOOKUP_PARENT, &nd); + if (err) + goto out; + + /* + * Search down, within the parent, looking for an + * autofs super block that has the device number + * corresponding to the autofs fs we want to open. + */ + err = autofs_dev_ioctl_find_super(&nd, devid); + if (err) { + path_release(&nd); + goto out; + } + + filp = dentry_open(nd.dentry, nd.mnt, O_RDONLY); + if (IS_ERR(filp)) { + err = PTR_ERR(filp); + goto out; + } + + autofs_dev_ioctl_fd_install(fd, filp); + } + + return fd; + +out: + put_unused_fd(fd); + return err; +} + +/* Open a file descriptor on an autofs mount point */ +static int autofs_dev_ioctl_openmount(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + const char *path; + dev_t devid; + int err, fd; + + /* param->path has already been checked */ + if (!param->openmount.devid) + return -EINVAL; + + param->ioctlfd = -1; + + path = param->path; + devid = param->openmount.devid; + + err = 0; + fd = autofs_dev_ioctl_open_mountpoint(path, devid); + if (unlikely(fd < 0)) { + err = fd; + goto out; + } + + param->ioctlfd = fd; +out: + return err; +} + +/* Close file descriptor allocated above (user can also use close(2)). */ +static int autofs_dev_ioctl_closemount(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + return sys_close(param->ioctlfd); +} + +/* + * Send "ready" status for an existing wait (either a mount or an expire + * request). + */ +static int autofs_dev_ioctl_ready(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + autofs_wqt_t token; + + token = (autofs_wqt_t) param->ready.token; + return autofs4_wait_release(sbi, token, 0); +} + +/* + * Send "fail" status for an existing wait (either a mount or an expire + * request). + */ +static int autofs_dev_ioctl_fail(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + autofs_wqt_t token; + int status; + + token = (autofs_wqt_t) param->fail.token; + status = param->fail.status ? param->fail.status : -ENOENT; + return autofs4_wait_release(sbi, token, status); +} + +/* + * Set the pipe fd for kernel communication to the daemon. + * + * Normally this is set at mount using an option but if we + * are reconnecting to a busy mount then we need to use this + * to tell the autofs mount about the new kernel pipe fd. In + * order to protect mounts against incorrectly setting the + * pipefd we also require that the autofs mount be catatonic. + * + * This also sets the process group id used to identify the + * controlling process (eg. the owning automount(8) daemon). + */ +static int autofs_dev_ioctl_setpipefd(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + int pipefd; + int err = 0; + + if (param->setpipefd.pipefd == -1) + return -EINVAL; + + pipefd = param->setpipefd.pipefd; + + mutex_lock(&sbi->wq_mutex); + if (!sbi->catatonic) { + mutex_unlock(&sbi->wq_mutex); + return -EBUSY; + } else { + struct file *pipe = fget(pipefd); + if (!pipe->f_op || !pipe->f_op->write) { + err = -EPIPE; + fput(pipe); + goto out; + } + sbi->oz_pgrp = process_group(current); + sbi->pipefd = pipefd; + sbi->pipe = pipe; + sbi->catatonic = 0; + } +out: + mutex_unlock(&sbi->wq_mutex); + return err; +} + +/* + * Make the autofs mount point catatonic, no longer responsive to + * mount requests. Also closes the kernel pipe file descriptor. + */ +static int autofs_dev_ioctl_catatonic(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + autofs4_catatonic_mode(sbi); + return 0; +} + +/* Set the autofs mount timeout */ +static int autofs_dev_ioctl_timeout(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + unsigned long timeout; + + timeout = param->timeout.timeout; + param->timeout.timeout = sbi->exp_timeout / HZ; + sbi->exp_timeout = timeout * HZ; + return 0; +} + +/* + * Return the uid and gid of the last request for the mount + * + * When reconstructing an autofs mount tree with active mounts + * we need to re-connect to mounts that may have used the original + * process uid and gid (or string variations of them) for mount + * lookups within the map entry. + */ +static int autofs_dev_ioctl_requester(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + struct autofs_info *ino; + struct nameidata nd; + const char *path; + dev_t devid; + int err = -ENOENT; + + if (param->size <= sizeof(*param)) { + err = -EINVAL; + goto out; + } + + path = param->path; + devid = sbi->sb->s_dev; + + param->requester.uid = param->requester.gid = -1; + + /* Get nameidata of the parent directory */ + err = path_lookup(path, LOOKUP_PARENT, &nd); + if (err) + goto out; + + err = autofs_dev_ioctl_find_super(&nd, devid); + if (err) + goto out_release; + + ino = autofs4_dentry_ino(nd.dentry); + if (ino) { + err = 0; + autofs4_expire_wait(nd.dentry); + spin_lock(&sbi->fs_lock); + param->requester.uid = ino->uid; + param->requester.gid = ino->gid; + spin_unlock(&sbi->fs_lock); + } + +out_release: + path_release(&nd); +out: + return err; +} + +/* + * Call repeatedly until it returns -EAGAIN, meaning there's nothing + * more that can be done. + */ +static int autofs_dev_ioctl_expire(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + struct vfsmount *mnt; + int how; + + how = param->expire.how; + mnt = fp->f_path.mnt; + + return autofs4_do_expire_multi(sbi->sb, mnt, sbi, how); +} + +/* Check if autofs mount point is in use */ +static int autofs_dev_ioctl_askumount(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + param->askumount.may_umount = 0; + if (may_umount(fp->f_path.mnt)) + param->askumount.may_umount = 1; + return 0; +} + +/* + * Check if the given path is a mountpoint. + * + * If we are supplied with the file descriptor of an autofs + * mount we're looking for a specific mount. In this case + * the path is considered a mountpoint if it is itself a + * mountpoint or contains a mount, such as a multi-mount + * without a root mount. In this case we return 1 if the + * path is a mount point and the super magic of the covering + * mount if there is one or 0 if it isn't a mountpoint. + * + * If we aren't supplied with a file descriptor then we + * lookup the nameidata of the path and check if it is the + * root of a mount. If a type is given we are looking for + * a particular autofs mount and if we don't find a match + * we return fail. If the located nameidata path is the + * root of a mount we return 1 along with the super magic + * of the mount or 0 otherwise. + * + * In both cases the the device number (as returned by + * new_encode_dev()) is also returned. + */ +static int autofs_dev_ioctl_ismountpoint(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + struct nameidata nd; + const char *path; + unsigned int type; + unsigned int devid, magic; + int err = -ENOENT; + + if (param->size <= sizeof(*param)) { + err = -EINVAL; + goto out; + } + + path = param->path; + type = param->ismountpoint.in.type; + + param->ismountpoint.out.devid = devid = 0; + param->ismountpoint.out.magic = magic = 0; + + if (!fp || param->ioctlfd == -1) { + if (autofs_type_any(type)) { + struct super_block *sb; + + err = path_lookup(path, LOOKUP_FOLLOW, &nd); + if (err) + goto out; + + sb = nd.dentry->d_sb; + devid = new_encode_dev(sb->s_dev); + } else { + struct autofs_info *ino; + + err = path_lookup(path, LOOKUP_PARENT, &nd); + if (err) + goto out; + + err = autofs_dev_ioctl_find_sbi_type(&nd, type); + if (err) + goto out_release; + + ino = autofs4_dentry_ino(nd.dentry); + devid = autofs4_get_dev(ino->sbi); + } + + err = 0; + if (nd.dentry->d_inode && + nd.mnt->mnt_root == nd.dentry) { + err = 1; + magic = nd.dentry->d_inode->i_sb->s_magic; + } + } else { + dev_t dev = autofs4_get_dev(sbi); + + err = path_lookup(path, LOOKUP_PARENT, &nd); + if (err) + goto out; + + err = autofs_dev_ioctl_find_super(&nd, dev); + if (err) + goto out_release; + + devid = dev; + + err = have_submounts(nd.dentry); + + if (nd.mnt->mnt_mountpoint != nd.mnt->mnt_root) { + if (follow_down(&nd.mnt, &nd.dentry)) { + struct inode *inode = nd.dentry->d_inode; + magic = inode->i_sb->s_magic; + } + } + } + + param->ismountpoint.out.devid = devid; + param->ismountpoint.out.magic = magic; + +out_release: + path_release(&nd); +out: + return err; +} + +/* + * Our range of ioctl numbers isn't 0 based so we need to shift + * the array index by _IOC_NR(AUTOFS_CTL_IOC_FIRST) for the table + * lookup. + */ +#define cmd_idx(cmd) (cmd - _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST)) + +static ioctl_fn lookup_dev_ioctl(unsigned int cmd) +{ + static struct { + int cmd; + ioctl_fn fn; + } _ioctls[] = { + {cmd_idx(AUTOFS_DEV_IOCTL_VERSION_CMD), NULL}, + {cmd_idx(AUTOFS_DEV_IOCTL_PROTOVER_CMD), + autofs_dev_ioctl_protover}, + {cmd_idx(AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD), + autofs_dev_ioctl_protosubver}, + {cmd_idx(AUTOFS_DEV_IOCTL_OPENMOUNT_CMD), + autofs_dev_ioctl_openmount}, + {cmd_idx(AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD), + autofs_dev_ioctl_closemount}, + {cmd_idx(AUTOFS_DEV_IOCTL_READY_CMD), + autofs_dev_ioctl_ready}, + {cmd_idx(AUTOFS_DEV_IOCTL_FAIL_CMD), + autofs_dev_ioctl_fail}, + {cmd_idx(AUTOFS_DEV_IOCTL_SETPIPEFD_CMD), + autofs_dev_ioctl_setpipefd}, + {cmd_idx(AUTOFS_DEV_IOCTL_CATATONIC_CMD), + autofs_dev_ioctl_catatonic}, + {cmd_idx(AUTOFS_DEV_IOCTL_TIMEOUT_CMD), + autofs_dev_ioctl_timeout}, + {cmd_idx(AUTOFS_DEV_IOCTL_REQUESTER_CMD), + autofs_dev_ioctl_requester}, + {cmd_idx(AUTOFS_DEV_IOCTL_EXPIRE_CMD), + autofs_dev_ioctl_expire}, + {cmd_idx(AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD), + autofs_dev_ioctl_askumount}, + {cmd_idx(AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD), + autofs_dev_ioctl_ismountpoint} + }; + unsigned int idx = cmd_idx(cmd); + + return (idx >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[idx].fn; +} + +/* ioctl dispatcher */ +static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user) +{ + struct autofs_dev_ioctl *param; + struct file *fp; + struct autofs_sb_info *sbi; + unsigned int cmd_first, cmd; + ioctl_fn fn = NULL; + int err = 0; + + /* only root can play with this */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + cmd_first = _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST); + cmd = _IOC_NR(command); + + if (_IOC_TYPE(command) != _IOC_TYPE(AUTOFS_DEV_IOCTL_IOC_FIRST) || + cmd - cmd_first >= AUTOFS_DEV_IOCTL_IOC_COUNT) { + return -ENOTTY; + } + + /* Copy the parameters into kernel space. */ + param = copy_dev_ioctl(user); + if (IS_ERR(param)) + return PTR_ERR(param); + + err = validate_dev_ioctl(command, param); + if (err) + goto out; + + /* The validate routine above always sets the version */ + if (cmd == AUTOFS_DEV_IOCTL_VERSION_CMD) + goto done; + + fn = lookup_dev_ioctl(cmd); + if (!fn) { + AUTOFS_WARN("unknown command 0x%08x", command); + return -ENOTTY; + } + + fp = NULL; + sbi = NULL; + + /* + * For obvious reasons the openmount can't have a file + * descriptor yet. We don't take a reference to the + * file during close to allow for immediate release. + */ + if (cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD && + cmd != AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD) { + fp = fget(param->ioctlfd); + if (!fp) { + if (cmd == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) + goto cont; + err = -EBADF; + goto out; + } + + if (!fp->f_op) { + err = -ENOTTY; + fput(fp); + goto out; + } + + sbi = autofs_dev_ioctl_sbi(fp); + if (!sbi || sbi->magic != AUTOFS_SBI_MAGIC) { + err = -EINVAL; + fput(fp); + goto out; + } + + /* + * Admin needs to be able to set the mount catatonic in + * order to be able to perform the re-open. + */ + if (!autofs4_oz_mode(sbi) && + cmd != AUTOFS_DEV_IOCTL_CATATONIC_CMD) { + err = -EACCES; + fput(fp); + goto out; + } + } +cont: + err = fn(fp, sbi, param); + + if (fp) + fput(fp); +done: + if (err >= 0 && copy_to_user(user, param, AUTOFS_DEV_IOCTL_SIZE)) + err = -EFAULT; +out: + free_dev_ioctl(param); + return err; +} + +static long autofs_dev_ioctl(struct file *file, uint command, ulong u) +{ + int err; + err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u); + return (long) err; +} + +#ifdef CONFIG_COMPAT +static long autofs_dev_ioctl_compat(struct file *file, uint command, ulong u) +{ + return (long) autofs_dev_ioctl(file, command, (ulong) compat_ptr(u)); +} +#else +#define autofs_dev_ioctl_compat NULL +#endif + +static const struct file_operations _dev_ioctl_fops = { + .unlocked_ioctl = autofs_dev_ioctl, + .compat_ioctl = autofs_dev_ioctl_compat, + .owner = THIS_MODULE, +}; + +static struct miscdevice _autofs_dev_ioctl_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = AUTOFS_DEVICE_NAME, + .fops = &_dev_ioctl_fops +}; + +/* Register/deregister misc character device */ +int autofs_dev_ioctl_init(void) +{ + int r; + + r = misc_register(&_autofs_dev_ioctl_misc); + if (r) { + AUTOFS_ERROR("misc_register failed for control device"); + return r; + } + + return 0; +} + +void autofs_dev_ioctl_exit(void) +{ + misc_deregister(&_autofs_dev_ioctl_misc); + return; +} + --- linux-2.6.22.orig/fs/autofs4/init.c +++ linux-2.6.22/fs/autofs4/init.c @@ -29,11 +29,20 @@ static struct file_system_type autofs_fs static int __init init_autofs4_fs(void) { - return register_filesystem(&autofs_fs_type); + int err; + + err = register_filesystem(&autofs_fs_type); + if (err) + return err; + + autofs_dev_ioctl_init(); + + return err; } static void __exit exit_autofs4_fs(void) { + autofs_dev_ioctl_exit(); unregister_filesystem(&autofs_fs_type); } --- /dev/null +++ linux-2.6.22/include/linux/auto_dev-ioctl.h @@ -0,0 +1,229 @@ +/* + * Copyright 2008 Red Hat, Inc. All rights reserved. + * Copyright 2008 Ian Kent <raven@themaw.net> + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + */ + +#ifndef _LINUX_AUTO_DEV_IOCTL_H +#define _LINUX_AUTO_DEV_IOCTL_H + +#include <linux/auto_fs.h> + +#ifdef __KERNEL__ +#include <linux/string.h> +#else +#include <string.h> +#endif /* __KERNEL__ */ + +#define AUTOFS_DEVICE_NAME "autofs" + +#define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 +#define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 + +#define AUTOFS_DEVID_LEN 16 + +#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) + +/* + * An ioctl interface for autofs mount point control. + */ + +struct args_protover { + __u32 version; +}; + +struct args_protosubver { + __u32 sub_version; +}; + +struct args_openmount { + __u32 devid; +}; + +struct args_ready { + __u32 token; +}; + +struct args_fail { + __u32 token; + __s32 status; +}; + +struct args_setpipefd { + __s32 pipefd; +}; + +struct args_timeout { + __u64 timeout; +}; + +struct args_requester { + __u32 uid; + __u32 gid; +}; + +struct args_expire { + __u32 how; +}; + +struct args_askumount { + __u32 may_umount; +}; + +struct args_ismountpoint { + union { + struct args_in { + __u32 type; + } in; + struct args_out { + __u32 devid; + __u32 magic; + } out; + }; +}; + +/* + * All the ioctls use this structure. + * When sending a path size must account for the total length + * of the chunk of memory otherwise is is the size of the + * structure. + */ + +struct autofs_dev_ioctl { + __u32 ver_major; + __u32 ver_minor; + __u32 size; /* total size of data passed in + * including this struct */ + __s32 ioctlfd; /* automount command fd */ + + /* Command parameters */ + + union { + struct args_protover protover; + struct args_protosubver protosubver; + struct args_openmount openmount; + struct args_ready ready; + struct args_fail fail; + struct args_setpipefd setpipefd; + struct args_timeout timeout; + struct args_requester requester; + struct args_expire expire; + struct args_askumount askumount; + struct args_ismountpoint ismountpoint; + }; + + char path[0]; +}; + +static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) +{ + memset(in, 0, sizeof(struct autofs_dev_ioctl)); + in->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; + in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; + in->size = sizeof(struct autofs_dev_ioctl); + in->ioctlfd = -1; + return; +} + +/* + * If you change this make sure you make the corresponding change + * to autofs-dev-ioctl.c:lookup_ioctl() + */ +enum { + /* Get various version info */ + AUTOFS_DEV_IOCTL_VERSION_CMD = 0x71, + AUTOFS_DEV_IOCTL_PROTOVER_CMD, + AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, + + /* Open mount ioctl fd */ + AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, + + /* Close mount ioctl fd */ + AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, + + /* Mount/expire status returns */ + AUTOFS_DEV_IOCTL_READY_CMD, + AUTOFS_DEV_IOCTL_FAIL_CMD, + + /* Activate/deactivate autofs mount */ + AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, + AUTOFS_DEV_IOCTL_CATATONIC_CMD, + + /* Expiry timeout */ + AUTOFS_DEV_IOCTL_TIMEOUT_CMD, + + /* Get mount last requesting uid and gid */ + AUTOFS_DEV_IOCTL_REQUESTER_CMD, + + /* Check for eligible expire candidates */ + AUTOFS_DEV_IOCTL_EXPIRE_CMD, + + /* Request busy status */ + AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, + + /* Check if path is a mountpoint */ + AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, +}; + +#define AUTOFS_IOCTL 0x93 + +#define AUTOFS_DEV_IOCTL_VERSION \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_VERSION_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_PROTOVER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_PROTOVER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_PROTOSUBVER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_OPENMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_CLOSEMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_READY \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_READY_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_FAIL \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_FAIL_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_SETPIPEFD \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_CATATONIC \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_CATATONIC_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_TIMEOUT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_TIMEOUT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_REQUESTER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_REQUESTER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_EXPIRE \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_EXPIRE_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_ASKUMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_ISMOUNTPOINT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, struct autofs_dev_ioctl) + +#endif /* _LINUX_AUTO_DEV_IOCTL_H */ --- linux-2.6.22.orig/include/linux/auto_fs.h +++ linux-2.6.22/include/linux/auto_fs.h @@ -17,11 +17,13 @@ #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/limits.h> +#include <linux/types.h> +#include <linux/ioctl.h> +#else #include <asm/types.h> +#include <sys/ioctl.h> #endif /* __KERNEL__ */ -#include <linux/ioctl.h> - /* This file describes autofs v3 */ #define AUTOFS_PROTO_VERSION 3